DQA framework brings diagnostic state tracking to multi-turn RAG for enterprise IT support
burkov · x · 2026-10-19
Andriy Burkov introduces DQA, a Diagnostic Question-Answering framework for multi-turn enterprise IT support. Standard RAG retrieves documents independently each turn, so it can't accumulate evidence, weigh competing explanations, or track which root causes remain plausible — while IT support conversations are fundamentally diagnostic, requiring evidence gathering across turns to find root causes. With enterprises holding hundreds of thousands of historical tickets, faster resolution directly affects cost and satisfaction. DQA explicitly maintains a diagnostic state across turns, and the article includes an evaluation.
More from coding & agent
- Dev suggests Claude Code compact context before notifying, not after — tonygwu · 2026-10-19
- Air Force recruit open-sources RaiGolmi, a VM workspace for running Claude Code agents unattended for months — BoshBoyBinton · 2026-10-19
- Consultant open-sources agent-first slide editor where Claude Code edits decks from comments — beh_zod · 2026-10-19
- Chat is the wrong shape for AI brainstorming: a dev experiments with tree-shaped idea maps — S_B_B_B_K · 2026-10-19
- Addy Osmani: writing code isn't the bottleneck anymore — build agent self-verification loops — bibryam · 2026-10-19
- Local models are now good enough for first-round code review, dev finds while paying frontier API prices — draginol · 2026-10-19